Electricity Demand Prediction Research Articles

Applicability of data-driven methods in modeling electricity demand-climate nexus: A tale of Singapore and Hong Kong

Predicting electricity demand at city level is vital for stakeholders. There are various data-driven methods in electricity consumption prediction, but their applicability to forecast monthly electricity demand has yet to be systematically explored. This study examines several widely used data-driven methods, namely multiple linear regression (MLR), machine learning (ML) method including support vector machine (SVM) and random forest (RF), and deep learning (DL) method including long short-term memory network (LSTM) and LSTM-gated recurrent unit (GRU), for long-term energy prediction using climatic and historical electricity datasets in Singapore (2005–2019) and Hong Kong (1975–2019). In Singapore, ML outperforms other methods in terms of statistical criteria and time series plots, and SVM provides the best accuracy with mean absolute percentile error (MAPE) of 2.55 %, while MLR exhibits the worst accuracy with MAPE of 3.1 %. In Hong Kong, DL surpasses ML in terms of statistical criteria, time series stability, and generalization ability. MLR achieves the best overall prediction accuracy with R2 up to 0.95 but shows poor ability for predicting peak and low electricity consumption, while LSTM exhibits the smallest bias in these months. RF shows strong overfitting issues in both cities. Overall, SVM and LSTM are recommended for small and large datasets, respectively.

Strengthening energy transition through effective urban electric demand prediction: A multidisciplinary exploration of AI, policy, and administrative strategies

This research endeavors to strengthen energy transition in urban management through the enhanced accuracy of electric load demand forecasting within a multi-faceted approach considering legal and policy decision making associate with the proposed problem. Firstly, a prediction model is devised utilizing an evolving Peephole LSTM (PLSTM). This sophisticated architecture incorporates peephole connections, allowing for enhanced information flow within the network. Subsequently, a hybrid evolutionary algorithm is introduced for fine-tuning the parameters of the peephole LSTM (PLSTM). This hybrid approach amalgamates the whale optimization algorithm (WOA) and cultural algorithm (CA), harnessing their complementary strengths for optimal parameter configuration. The study extends beyond model development to address the practical implications of real-time electric load forecasting. A comprehensive stability analysis is conducted on datasets sourced from an urban area, offering insights into the model's reliability and performance under dynamic conditions. This tripartite investigation not only contributes to the advancement of predictive modeling in electric load demand forecasting but also underscores the significance of robust parameter optimization and stability assessments for real-world applicability in urban energy management. The simulation results on the practical dataset clearly show the high robustness and capabilities of the proposed model. By combining cutting-edge model architecture, hybrid evolutionary optimization, and thorough stability assessments, this study not only contributes to the forefront of predictive modeling in electric load forecasting but also emphasizes the critical importance of parameter optimization and stability evaluations for the seamless integration of such models into the dynamic landscape of urban energy management.

Research on Short Term Prediction of Electricity Demand in Hubei Province

The balance of electricity supply and demand is the basic condition for promoting the economic development of our country and improving the living standards of the people, and scientific forecasting of electricity demand is the premise of ensuring the balance of electricity supply and demand. Hubei Province is superior in geographical location, and its electricity demand and economic aggregate both rank high in the country, but due to the direct impact of the epidemic, its electricity demand has been affected. This paper uses OLS regression to obtain the linear regression equation of the three indicators of GDP and the proportion of the secondary industry structure before the epidemic from 2005 to 2018, and uses the Gray Forecast Model-assisted scenario analysis method to analyze the electricity consumption of Hubei Province under the influence of multiple factors, and predicts the electricity consumption of Hubei Province from 2019 to 2021 after removing the impact of the epidemic, and makes a short-term forecast of the electricity demand of the province from 2024 to 2029.

School Electricity Consumption in a Small Island Country: The Case of Fiji

Electricity consumption in buildings is one of the major causes of energy usage and knowledge of this can help building owners and users increase energy efficiency and conservation efforts. For Pacific Island countries, building electricity demand data is not readily accessible or available for constructing models to predict electricity demand. This paper starts to fill this gap by studying the case of schools in Fiji. The aim of the paper is to assess the factors affecting electricity demand for grid-connected Fijian schools and use this assessment to build mathematical models (multiple linear regression (MLR) and artificial neural network (ANN)) to predict electricity consumption. The average grid-connected electricity demand in kWh/year was 1411 for early childhood education schools, 5403 for primary schools, and 23,895 for secondary schools. For predicting electricity demand (ED) for all grid-connected schools, the stepwise MLR model shows that taking logarithm transformations on both the dependent variable and independent variables (number of students, lights, and air conditioning systems) yields statistically significant independent variables with an R2 value of 73.3% and RMSE of 0.2248. To improve the predicting performance, ANN models were constructed on both the natural form of variables and transformed variables. The optimum ANN model had an R2 value of 95.3% and an RMSE of 59.4 kWh/year. The findings of this study can assist schools in putting measures in place to reduce their electricity demand, associated costs, and carbon footprint, as well as help government ministries make better-informed policies.

AKURASI PERAMALAN BEBAN LISTRIK SEKTOR RUMAH TANGGA MENGGUNAKAN ARTIFICIAL NEURAL NETWORK DI KOTA PALANGKA RAYA

Electrical energy is one of the most important energies in the daily life of the people of Palangkaraya, both in business, social, government and household sects. Planning electrical energy in its needs is needed to avoid an energy crisis, because economic growth in the Palangkaraya City area requires electrical energy in its operations. The planning carried out in the study by predicting electricity demand used the ANN (Artificial Neural Network) method. ANN is used at the prediction stage within the scope of the household sector. JST results have good forecasting accuracy with MAPE (Mean Absolute Percentage Error) of 7.1975%. With an absolute error value occurred at Rates of R.2/3,500VA to 5,500VA in July amounting to 32.2728%.

Developing a hybrid technique for energy demand forecasting based on optimized improved SVM by the boosted multi-verse optimizer: Investigation on affecting factors

Electricity demand prediction accuracy is crucial for operational energy resource management and strategy. In this study, we provide a multi-form model for electricity demand prediction in China that based on incorporating of an upgraded Support Vector Machine (SVM) and a Boosted Multi-Verse Optimizer (BMVO). The suggested model is proposed to address the shortcomings of existing prediction approaches, which frequently fail to internment the complicated nonlinear interactions between demand for electricity and the variables that influence it. The improved SVM algorithm incorporates a modified genetic algorithm based on kernel function for enhancing the stability of the model. The BMVO technique is employed to optimize the combined model's weights and increase its generalization effectiveness. The suggested approach is tested by real-world Chinese energy demand data. The findings show that it outperforms existing prediction approaches in terms of reliability and precision. Further, the number of samples chosen affects how well the proposed BMVO linked with the Incremental SVM (ISVM) predicts outcomes. Particularly, when 1735 samples are chosen, the lowest level of Mean Absolute Percent Error (MAPE) was noted. The Root Mean Square Error (RMSE) and MAPE values under the proposed BMVO/ISVM model are reduced by 53.72% and 55.22%, respectively, compared to the Artificial Neural Network (ANN) approach reported in literature. Finally, the suggested model is capable of accurately predicting the electricity demand in China and has the potential to be applied to other energy-demand prediction applications.

A physics-informed graph learning approach for citywide electric vehicle charging demand prediction and pricing

A growing number of electric vehicles (EVs) is putting pressure on smart charging services. As a foundation of informing drivers of vacant charging facilities and rationalizing pricing, an effective approach for predicting citywide spatio-temporal EV charging demand that incorporates pricing information is required. Although many deep learning models have been carried out with the orientation of improving prediction accuracy and achieved good results, there is still a lack of prediction models that are economically interpretable and can consider the spillover effect of price adjustments on EV charging demand. To fill the research gaps, we propose a learning approach for accurate EV charging demand prediction and reasonable pricing, named PIAST, which enables the integration of convolutional feature engineering, spatio-temporal dual attention mechanism and physics-informed neural network training. On a dataset containing 18,061 EV charging piles, we demonstrate the state-of-the-art performance of the proposed model. The results empirically showed that the proposed approach achieved an average improvement of 14.78% in accuracy, compared to other representative models. Moreover, the model can uncover the price elasticity of demand during training, making the model interpretable. Finally, price adjustment experiments are conducted to demonstrate the self-influence and spillover effects of price.

Predicting electricity demand in Cameroon with enhanced modified exponential models: A focus on the southern integrated grid (S.I.G)

This paper is centered on the prediction of electricity demand within the Southern Integrated Grid (S.I.G) for the forthcoming six years (2022–2027) through the utilization of advanced forecasting techniques. These methodologies encompass modified exponential, probabilistic or stochastic extrapolation and linear regression models. The foundation of these forecasts is established on a comprehensive examination of load curve data spanning 12 years (2010–2021) and an analysis of the factors influencing electricity demand in Cameroon. The models are implemented using Matlab and Excel, enabling the projection of results. The results of this analysis reveal a consistent growth trend in Cameroon's electricity demand between 2022 and 2027. the modified exponential model foresees an increase from 991.16MW to 1189.25MW, the probabilistic model from 969.68MW to 1109.20MW, and the linear regression model from 853.46MW to 975.89MW. Despite the inherent limitations, the outcomes prove to be satisfactory, marked by a high level of accuracy and reliability, as evidenced by mean absolute percentage error (MAPE) values of 0.2% for the modified exponential and probabilistic methods and 0.55% for the linear regression method. These scores fall well below the industry-accepted benchmark of MAPE < 10% outlined by the Lewis benchmark. In a comparative analysis, it is evident that the modified exponential and probabilistic models exhibit superior accuracy.

Enhancing Electrical Power Demand Prediction Using LSTM-Based Deep Learning Models for Local Energy Communities

The pursuit of accurate electrical power demand forecasting has led to the application of deep learning algorithms, notably demonstrating promising outcomes despite the prerequisite of substantial training data. This study pioneers a new learning paradigm, employing sophisticated deep learning models specifically, Long Short-Term Memory networks and recurrent neural networks (RNNs). Leveraging historical load data, temperature, wind speed, and day-ahead predicted spot prices, this approach follows a structured flow involving data preprocessing, sequence generation, model training, and subsequent prediction of future load demand using LSTM-based RNN variants. The study’s paramount findings underscore the substantial advancement achieved by this proposed methodology over prevailing techniques. The method significantly improves prediction accuracy by over 11%, demonstrating the efficacy of deep learning models and a significant leap forward in forecasting precision. Beyond its superior predictive capabilities, this novel strategy serves as a catalyst for enhancing energy distribution management in local energy communities. Its effectiveness lies not only in its precision but also in enabling the optimization and cost-effective control of energy distribution, vital for sustainable energy management in these communities. Ultimately, this pioneering approach presents a robust solution poised to revolutionize the landscape of electrical power demand forecasting and its practical application in local energy systems.

Electricity demand error corrections with attention bi-directional neural networks

Reliable forecast of electricity demand is crucial to stability, supply, and management of electricity grids. Short-term hourly and sub-hourly demand forecasts are difficult due to the stochastic nature of electricity demand. To improve the electricity demand forecasts, artificial neural networks are combined with attention-based bi-directional neural network as well as Error Correction methods, and Bayesian hyperparameter optimizations. As part of the hybrid VMD-CABLSTM-ANN-EC model, the intrinsic mode functions, representing distinct predictive features, are separated from electricity demand data using variational mode decomposition algorithm. For predicting each intrinsic mode function and respective error time series, convolutional neural networks-bi-directional long short-term memory algorithms are applied. In a second stage, error time series are split, followed by a model to predict the error series’ intrinsic mode functions, and a final integration stage to predict the error. The results of the proposed VMD-CABLSTM-ANN-EC model are benchmarked against decomposition-based and standalone models at substations in Queensland, Australia. The proposed VMD-CABLSTM-ANN-EC model outperformed all benchmark models. By splitting the predictor and target variables, it will be shown that the variational model decomposition method improves error corrections by revealing key features of historical demand data. Using error correction method in short-term electricity demand modelling can provide greater confidence in the prediction of electricity demand. The models can be used by energy providers for market analysis and insight research, to manage power failure risk, and make financial decisions.

A multi-step electricity prediction model for residential buildings based on ensemble Empirical Mode Decomposition technique

Residential electricity demand is increasing rapidly, constituting about a quarter of total energy consumption. Electricity demand prediction is one of the sustainable solutions to improve energy efficiency in real-world scenarios. The non-linear and non-stationary consumption patterns in residential buildings make electricity prediction more challenging. This paper proposes a multi-step prediction approach that first conducts cluster analysis to identify seasonal consumption patterns. Secondly, an improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) method and autoencoder model has been deployed to remove irregular patterns, noise, and redundancy from electricity load time series. Finally, the Long Short-Term Memory (LSTM) model has been trained to predict electricity consumption by considering historical, seasonal, and temporal data dependencies. Further, experimental analysis has been conducted on real-time electricity consumption datasets of residential buildings. The comparative results reveal that the proposed multi-step model outperformed the existing state-of-the-art RF-LSTM-based prediction model and attained higher accuracy.

A Deep Learning Approach to Real-time Electricity Load Forecasting

In light of the increasing importance of accurate and real-time electrical demand forecasting, this research presents a deep learning model with the goal of dramatically improving predictive accuracy. Conventional methods of forecasting, such as linear regression, have trouble capturing the complex patterns included in data about electricity usage. Standard machine learning methods are shown to be wanting when compared to the suggested deep Long Short-Term Memory (LSTM) model. Mean Absolute Error (MAE) of 5.454 and Mean Squared Error (MSE) of 18.243 demonstrate the deep LSTM model's proficiency in tackling this problem. The linear regression, on the other hand, achieved a MAE of 47.352 and an MSE of 65.606, which is lower than the proposed model. Because of its greater predictive precision and reliability, the deep LSTM model is a viable option for accurate, real-time prediction of electricity demand.

Efficient daily electricity demand prediction with hybrid deep-learning multi-algorithm approach

Efficient daily electricity demand prediction with hybrid deep-learning multi-algorithm approach

Long-term electricity demand forecasting under low-carbon energy transition: Based on the bidirectional feedback between power demand and generation mix

Predicting electricity demand is crucial for ensuring energy security. However, the low-carbon energy transition has brought a new bidirectional feedback between power demand and generation mix, which may make the previous electricity demand forecasting methods no longer applicable. This study combines the system dynamics (SDs) model and power generation mix planning (PGMP) model to construct a hybrid forecasting method. It has smaller prediction error than other models, and can simultaneously predict the collaborative evolution of electricity demand, power generation mix and carbon emissions. Besides, the long-term planning of thermal power generators may not ensure power system's secure operation, the PGMP model is utilized to modify the Markov chain state transition matrix, which can predict future power generation mix and provide stable electricity supply. The prediction results for China show that under low and high emission reduction scenarios, the carbon dioxide emissions will peak in 2030 (12.228 billion tons and 11.741 billion tons), and the electricity demand will reach 12.63 trillion kWh and 12.76 trillion kWh in 2035. The installed proportion of thermal power generators will not reduce quickly, but gradually converted into backup generators. What's more, the results can also provide policy reference for accelerating low-carbon energy transition.

Short-Term Electricity Demand Forecasting Using Deep Neural Networks: An Analysis for Thai Data

Electricity demand forecasting plays a significant role in energy markets. Accurate prediction of electricity demand is the key factor in optimizing power generation and consumption, saving energy resources, and determining energy prices. However, integrating energy mix scenarios, including solar and wind power, which are highly nonlinear and seasonal, into an existing grid increases the uncertainty of generation, creating additional challenges for precise forecasting. To tackle such challenges, state-of-the-art methods and algorithms have been implemented in the literature. Artificial Intelligence (AI)-based deep learning models can effectively handle the information of long time-series data. Based on patterns identified in datasets, various scenarios can be developed. In this paper, several models were constructed and tested using deep AI networks in two different scenarios: Scenario1 used data for weekdays, excluding holidays, while Scenario2 used the data without exclusion. To find the optimal configuration, the models were trained and tested within a large space of alternative hyperparameters. We used an Artificial Neural Network (ANN)-based Feedforward Neural Network (FNN) to show the minimum prediction error for Scenario1 and a Recurrent Neural Network (RNN)-based Gated Recurrent Network (GRU) to show the minimum prediction error for Scenario2. From our results, it can be concluded that the weekday dataset in Scenario1 prepared by excluding weekends and holidays provides better forecasting accuracy compared to the holistic dataset approach used in Scenario2. However, Scenario2 is necessary for predicting the demand on weekends and holidays.

Secure and efficient prediction of electric vehicle charging demand using [formula omitted]-LSTM and AES-128 cryptography

In recent years, there has been a significant surge in demand for electric vehicles (EVs), necessitating accurate prediction of EV charging requirements. This prediction plays a crucial role in evaluating its impact on the power grid, encompassing power management and peak demand management. In this paper, a novel deep neural network based on α2 -LSTM is proposed to predict the demand for charging from electric vehicles at a 15-minute time resolution. Additionally, we employ AES-128 for station quantization and secure communication with users. Our proposed algorithm achieves a 9.2% reduction in both the Root Mean Square Error (RMSE) and the mean absolute error compared to LSTM, along with a 13.01% increase in demand accuracy. We present a 12-month prediction of EV charging demand at charging stations, accompanied by an effective comparative analysis of Mean Absolute Percentage Error (MAPE) and Mean Percentage Error (MPE) over the last five years using our proposed model. The prediction analysis has been conducted using Python programming.

Integrated Multi-Head Self-Attention Transformer model for electricity demand prediction incorporating local climate variables

This paper develops a trustworthy deep learning model that considers electricity demand (G) and local climate conditions. The model utilises Multi-Head Self-Attention Transformer (TNET) to capture critical information from G, to attain reliable predictions with local climate (rainfall, radiation, humidity, evaporation, and maximum and minimum temperatures) data from Energex substations in Queensland, Australia. The TNET model is then evaluated with deep learning models (Long-Short Term Memory LSTM, Bidirectional LSTM BILSTM, Gated Recurrent Unit GRU, Convolutional Neural Networks CNN, and Deep Neural Network DNN) based on robust model assessment metrics. The Kernel Density Estimation method is used to generate the prediction interval (PI) of electricity demand forecasts and derive probability metrics and results to show the developed TNET model is accurate for all the substations. The study concludes that the proposed TNET model is a reliable electricity demand predictive tool that has high accuracy and low predictive errors and could be employed as a stratagem by demand modellers and energy policy-makers who wish to incorporate climatic factors into electricity demand patterns and develop national energy market insights and analysis systems.

Power Load Forecasting System Based on Deep Hybrid Learning Model

Accurate prediction of electricity demand is crucial to ensure the stability and dependability of local power grids. Numerous scholars have put forth comprehensive prediction systems; However, the majority of these models fail to capture the inherent global features present within the data. This study introduces a novel integrated prediction system that leverages the synergistic capabilities of Time Convolutional Network (TCN) and Long Short-Term Memory (LSTM) architectures, aiming to enhance the accuracy of short-term electric load forecasting. The initial step is to establish separate prediction models for LSTM and TCN, with a focus on electric load data. After combining the output results of these models, the reciprocal of the error square ratio was used as a weighting factor. By using this approach, the LSTM-TCN model for combined prediction is created. This research paper performs an exhaustive examination of the case study by employing authentic data sourced from the Australian Energy Management Authority. The study's findings support that the LSTM-TCN model outperforms both single prediction models and traditional network models in terms of performance. The results indicate that the LSTM-TCN model exhibits greater accuracy in predicting short-term energy demand.

The role of energy communities in electricity grid balancing: A flexible tool for smart grid power distribution optimization

The unpredictability of renewable energy systems can affect the stability of the electricity grid, causing voltage and frequency imbalances. In this work, a suitable methodology based on the peer-to-peer scheme applied to energy communities is developed and implemented in a simulation tool useful for investigating energy management strategies for decision-making aims. The developed model discretizes the energy community and its users into multiple control volumes, taking into account various technologies. It incorporates energy balances for individual users as well as the entire energy community, considering prosumers, consumers, energy storage systems, and electric vehicles. Moreover, the model enables the exploration of different solutions for grid frequency regulation and optimization of distributed energy resources. Additionally, the tool can predict electricity demand one day ahead, facilitating the organization of renewable energy availability and storage systems to minimize grid interactions and flatten electricity demand. The model incorporates different objective functions, including self-consumption, self-sufficiency, and grid-balancing factors, to evaluate the performance of energy communities. To show the capability of the developed model, it will be adopted to optimize the performance of an investigated community. As a result, an increase in renewable energy self-consumption from 59.4 to 83.9 MW h/year is achieved. Furthermore, the objective of grid balancing was achieved by guaranteeing a non-fluctuating load and providing 1.46 and 7.71 MW h/year for upward and downward grid frequency regulation. These findings illustrate the positive impact of energy dispatching management on the integration of renewable energy sources and the importance of further studying this topic to ensure grid stability.

Predictive control of power demand peak regulation based on deep reinforcement learning

As urbanization continues to accelerate, effectively managing peak electricity demand becomes increasingly critical to avoid power outages and system overloads that can negatively impact both buildings and power systems. To tackle this challenge, we propose a novel model-free predictive control method called “Dynamic Dual Predictive Control-Deep Deterministic Policy Gradient (D2PC-DDPG)" based on a deep reinforcement learning framework. Our method employs the Deep Forest-Deep Q-Network (DF-DQN) model to predict electricity demand across multiple buildings, and based on the output of the DF-DQN model, applies the Deep Deterministic Policy Gradient (DDPG) algorithm to optimize coordinated control of energy storage systems, including hot and chilled water storage tanks in multiple buildings. Experimental results show that our proposed DF-DQN model outperforms other traditional machine learning, deep learning, and reinforcement learning methods in terms of prediction accuracy, such as mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE). Moreover, our D2PC-DDPG method achieves superior control performance and peak load reduction compared to other reinforcement learning methods and an RBC-based control method. Specifically, our method successfully reduced peak load by 27.1% and 21.4% over a two-week period in the same regions. To demonstrate the generalizability of our D2PC-DDPG method, we tested it in five different regions and compared its performance with an RBC-based control method. The results showed that our method achieved an average reduction of 16.6%, 7%, 9.2%, and 11% for ramping, 1-load_factor, average_daily_peak, and peak_demand, respectively. These findings demonstrate the effectiveness and practicality of our proposed method in addressing critical energy management issues in various urban environments.